© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 4372
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and data normalization in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.54
    bootstrapcdn
    -0.51
     createState
    -0.44
    stateProvider
    -0.44
     ब्रेकडाउन
    -0.42
    RegressionTest
    -0.39
    $_['
    -0.39
     CanadaChoose
    -0.39
    ніципалі
    -0.37
     gelöst
    -0.36
    POSITIVE LOGITS
     normalization
    1.31
     normalize
    1.23
     Normalize
    1.07
     scaling
    1.02
     normalized
    1.01
    normalization
    0.99
    normalize
    0.98
    Normalization
    0.98
     scaled
    0.94
    Normalize
    0.93
    Activations Density 2.089%

    No Known Activations